mobgap.gait_sequences.evaluation.gsd_score

mobgap.gait_sequences.evaluation.gsd_score = Scorer(default_aggregator=<function mean_agg>, final_aggregator=<function gsd_final_agg>, n_jobs=None, pre_dispatch='2*n_jobs', progress_bar=True, score_func=<function gsd_per_datapoint_score>, single_score_callback=None, verbose=0)

Scorer for GSD algorithms.

This is a pre-configured Scorer object using the gsd_per_datapoint_score function as per-datapoint scorer and the gsd_final_agg function as final aggregator. For more information about Scorer, head to the tpcp documentation (Scorer). For usage information in the context of mobgap, have a look at the evaluation example for GSD.

The following metrics are calculated:

Raw metrics (part of the single results):

• single__raw__detected: The detected gait sequences as a single dataframe with the datapoint labels as index.

• single__raw__reference: The reference gait sequences as a single dataframe with the datapoint labels as index.

Metrics per datapoint (single results): These values are all provided as a list of values, one per datapoint.

• All outputs of calculate_unmatched_gsd_performance_metrics and calculate_matched_gsd_performance_metrics averaged per datapoint. These are stored as single__{metric_name}

• single__runtime_s: The runtime of the algorithm in seconds.

Aggregated metrics (aggregated results):

• All single outputs averaged over all datapoints. These are stored as agg__{metric_name}.

• All metrics from calculate_unmatched_gsd_performance_metrics and calculate_matched_gsd_performance_metrics recalculated on all detected GSs across all datapoints. These are stored as combined__{metric_name}. Compared to the per-datapoint results (which are calculated, as errors per recording -> average over all recordings), these metrics are calculated as combining all GSDs from all recordings and then calculating the performance metrics. Effectively, this means, that in the per_datapoint version, each recording is weighted equally, while in the combined version, each GS is weighted equally.